Pauline M. Berry

An intelligent personal assistant for task and time management

We describe an intelligent personal assistant that has been developed to aid a busy knowledge worker in managing time commitments and performing tasks. The design of the system was motivated by the complementary objectives of (1) relieving the user of routine tasks, thus allowing her to focus on tasks that critically require human problem-solving skills, and (2) intervening in situations where cognitive overload leads to oversights or mistakes by the user. The system draws on a diverse set of AI technologies that are linked within a Belief-Desire-Intention (BDI) agent system. Although the system provides a number of automated functions, the overall framework is highly user centric in its support for human needs, responsiveness to human inputs, and adaptivity to user working style and preferences.

PTIME: Personalized assistance for calendaring

In a world of electronic calendars, the prospect of intelligent, personalized time management assistance seems a plausible and desirable application of AI. PTIME (Personalized Time Management) is a learning cognitive assistant agent that helps users handle email meeting requests, reserve venues, and schedule events. PTIME is designed to unobtrusively learn scheduling preferences, adapting to its user over time. The agent allows its user to flexibly express requirements for new meetings, as they would to an assistant. It interfaces with commercial enterprise calendaring platforms, and it operates seamlessly with users who do not have PTIME. This article overviews the system design and describes the models and technical advances required to satisfy the competing needs of preference modeling and elicitation, constraint reasoning, and machine learning. We further report on a multifaceted evaluation of the perceived usefulness of the system.

Deploying a personalized time management agent

We report on our ongoing practical experience in designing, implementing, and deploying PTIME, a personalized agent for time management and meeting scheduling in an open, multi-agent environment. In developing PTIME as part of a larger assistive agent called CALO, we have faced numerous challenges, including usability, multi-agent coordination, scalable constraint reasoning, robust execution, and unobtrusive learning. Our research advances basic solutions to the fundamental problems; however, integrating PTIME into a deployed system has raised other important issues for the successful adoption of new technology. As a personal assistant, PTIME must integrate easily into a users real environment, support her normal workflow, respect her authority and privacy, provide natural user interfaces, and handle the issues that arise with deploying such a system in an open environment.

Interactive execution monitoring of agent teams

There is an increasing need for automated support for humans monitoring the activity of distributed teams of cooperating agents, both human and machine. We characterize the domain-independent challenges posed by this problem, and describe how properties of domains influence the challenges and their solutions. We will concentrate on dynamic, data-rich domains where humans are ultimately responsible for team behavior. Thus, the automated aid should interactively support effective and timely decision making by the human. We present a domain-independent categorization of the types of alerts a plan-based monitoring system might issue to a user, where each type generally requires different monitoring techniques. We describe a monitoring framework for integrating many domain-specific and task-specific monitoring techniques and then using the concept of value of an alert to avoid operator overload. We use this framework to describe an execution monitoring approach we have used to implement Execution Assistants (EAs) in two different dynamic, data-rich, real-world domains to assist a human in monitoring team behavior. One domain (Army small unit operations) has hundreds of mobile, geographically distributed agents, a combination of humans, robots, and vehicles. The other domain (teams of unmanned ground and air vehicles) has a handful of cooperating robots. Both domains involve unpredictable adversaries in the vicinity. Our approach customizes monitoring behavior for each specific task, plan, and situation, as well as for user preferences. Our EAs alert the human controller when reported events threaten plan execution or physically threaten team members. Alerts were generated in a timely manner without inundating the user with too many alerts (less than 10% of alerts are unwanted, as judged by domain experts).

A Predictive Model for Satisfying Conflicting Objectives in Scheduling Problems

The economic viability of a manufacturing organization depends on its ability to maximize customer services; maintain efficient, low-cost operations; and minimize total investment. These objectives conflict with one another and, thus, are difficult to achieve on an operational basis. Much of the work in the area of automated scheduling systems recognizes this problem but does not address it effectively. The work presented by this Ph.D. dissertation was motivated by the desire to generate good, cost-effective schedules in dynamic and stochastic manufacturing environments.

Conflict negotiation among personal calendar agents

We will demonstrate distributed conflict resolution in the context of personalized meeting scheduling. The demonstration will show how distributed constraint optimization can be used to facilitate interaction between cognitive agents and their users. The system is part of the CALO personal cognitive assistant that will also be explored during the demonstration.

Evaluating intelligent knowledge systems: experiences with a user-adaptive assistant agent

This article examines experiences in evaluating a user-adaptive personal assistant agent designed to assist a busy knowledge worker in time management. We examine the managerial and technical challenges of designing adequate evaluation and the tension of collecting adequate data without a fully functional, deployed system. The CALO project was a seminal multi-institution effort to develop a personalized cognitive assistant. It included a significant attempt to rigorously quantify learning capability, which this article discusses for the first time, and ultimately the project led to multiple spin-outs including Siri. Retrospection on negative and positive experiences over the 6 years of the project underscores best practice in evaluating user-adaptive systems. Lessons for knowledge system evaluation include: the interests of multiple stakeholders, early consideration of evaluation and deployment, layered evaluation at system and component levels, characteristics of technology and domains that determine the appropriateness of controlled evaluations, implications of ‘in-the-wild’ versus variations of ‘in-the-lab’ evaluation, and the effect of technology-enabled functionality and its impact upon existing tools and work practices. In the conclusion, we discuss—through the lessons illustrated from this case study of intelligent knowledge system evaluation—how development and infusion of innovative technology must be supported by adequate evaluation of its efficacy.

Multi-level adaptation in teams of unmanned air and ground vehicles

We describe ongoing work to develop algorithms and software for the reprogrammable, coordinated command and control of teams of autonomous vehicles (AVs). This new software capability extends current work in distributed artificial intelligence and is intended to allow developers to build and test AV teams that collaboratively perform tasks - such as reconnaissance and surveillance - with minimal supervision in dynamic, unstructured environments. We describe a multilevel robot architecture which is adaptive along a number of dimensions, as well as several new technologies that have been developed to support behavior blending and inter-robot negotiation. 1. INTRODUCTION Over the last few years, and under ONR funding, we have been developing algorithms and software for the reprogrammable, coordinated command and control of teams of autonomous vehicles (AVs). This new software capability extends work in distributed artificial intelligence and is intended to allow developers to build and test AV teams that collaboratively perform tasks - such as reconnaissance and surveillance - with minimal supervision in dynamic, unstructured environments. In this paper, we describe our progress in realizing this vision. As motivation, Figure 1 illustrates a futuristic scenario involving the suppression of enemy air defenses (SEAD) using a team of UAVs. The icons representing the surveillance mission, helicopter mission, cover mission, and strike mission are all assumed to represent unmanned combat air vehicles (UCAVs). Control centers are shown on land, air, and sea. The order of events is as follows. The two surveillance UCAVs are launched from the ship to the surface-to-air missile (SAM) site to collect intelligence for prestrike planning. Using the information obtained, the operator then schedules the cover and strike missions. Two escorts responsible for the cover mission are subsequently launched and meet with a pair of UCAVs responsible for the air strike. During ingress, this SEAD package encounters an enemy mobile SAM site that attempts to break up the package. The escorts prcvide cover so that the strike mission can proceed. At the same time, a helicopter UCAV is launched to conduct mine countermeasure operations.

Teambotica: a robotic framework for integrated teaming, tasking, networking, and control

Teambotica is a research environment for the exploration of theories, designs and implementations of team-based robotics. In developing Teambotica, we found that many of the simplifying assumptions that are often taken in both multiagent systems and behavior-based robotics had to be discarded. Central to our approach is a multilevel agent architecture which is adaptive along a number of dimensions and which is based on a vertically integrated design that spans a wide range of operations, from team-level reasoning to low-level control. The design addresses a number of pertinent issues: the proper mix of deliberation and action, flexible networking support including planning for communications, adaptive task level control, team-based monitoring, and an open systems modularity that takes form-factor considerations seriously. We also describe simulation tools for development and discuss several robotic teams that we have demonstrated.

Reports on the 2005 AAAI Spring Symposium Series

The Association for the Advancement of Artificial Intelligence presented its 2005 Spring Symposium Series on Monday through Wednesday, March 21-23, 2005 at Stanford University in Stanford, California. The topics of the eight symposia in this symposium series were (1) AI Technologies for Homeland Security; (2) Challenges to Decision Support in a Changing World; (3) Developmental Robotics; (4) Dialogical Robots: Verbal Interaction with Embodied Agents and Situated Devices; (5) Knowledge Collection from Volunteer Contributors; (6) Metacognition in Computation; (7) Persistent Assistants: Living and Working with AI; and (8) Reasoning with Mental and External Diagrams: Computational Modeling and Spatial Assistance.